Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1913 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.8052. Min Act: -0.1700

Data Index: 2097092 (Open Web Text)

Max Activating Token Index: 954

Text #1

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.7854. Min Act: -0.1700

Data Index: 3961730 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.7412. Min Act: -0.1700

Data Index: 2498123 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.7009. Min Act: -0.1700

Data Index: 5579608 (Open Web Text)

Max Activating Token Index: 130

Text #4

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6938. Min Act: -0.1700

Data Index: 3391554 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6765. Min Act: -0.1700

Data Index: 3015010 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6757. Min Act: -0.1700

Data Index: 6611026 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6827. Min Act: -0.1700

Data Index: 1012192 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6389. Min Act: -0.1700

Data Index: 5364705 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6626. Min Act: -0.1700

Data Index: 2077141 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6531. Min Act: -0.1700

Data Index: 1591121 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6247. Min Act: -0.1700

Data Index: 2700162 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6233. Min Act: -0.1700

Data Index: 4303974 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6262. Min Act: -0.1700

Data Index: 2923167 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.5918. Min Act: -0.1700

Data Index: 4127702 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6276. Min Act: -0.1700

Data Index: 8354488 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6060. Min Act: -0.1700

Data Index: 4762796 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6226. Min Act: -0.1700

Data Index: 3708750 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.6253. Min Act: -0.1700

Data Index: 2985737 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.5834. Min Act: -0.1700

Data Index: 4300317 (Open Web Text)

Max Activating Token Index: 220